A new AI model developed by a research team in Canada can accurately predict whether a patient will survive cancer by reading doctor’s notes.
Researchers at the University of British Columbia developed an AI model for part of a study published Thursday. The study’s authors wrote that accurately predicting whether a patient will survive helps improve cancer treatment. For example, it may recommend an earlier referral to palliative care resources or suggest prior evaluation of more aggressive treatments, writes UPI.
in 24News Breaker. Technology emerged telegraph channel. Subscribe so you don’t miss the latest and exciting news from the world of science!
“Our results show that it is possible to predict survival of patients with cancer without the need to create structured datasets or limit estimates to specific cancer types or locations,” the study’s authors write. . It opens up the possibility of easier training and use of such models for different types of cancer in different cancer centers.”
In the study, the authors noted that “almost all patients undergoing cancer treatment go to an initial consultation with their oncologist and disclose many details about survival, such as tobacco use or marital status, even if the clinic does not hide such a thing.” data.”
To conduct the study, the scientists trained an AI model using data from 47,625 patients across all BC cancer departments. The researchers noted that they excluded all patients diagnosed with more than one cancer from the study.
“We calculated survival as the number of months between the creation of the selected document and the patient’s recorded date of death, or April 6, 2022, when death data was last retrieved from administrative records,” says the study. Whether the patient is 6, 36, or 60 months old or not.”
Scientists have previously used such documents to predict the occurrence of at least three non-cancer diseases, according to the study.
The lead author of the study, psychiatrist and researcher Dr. “Artificial intelligence basically reads the advisory the way a human would,” Jon-Jose Nunez said in a press release. Many details, such as the patient’s age, type of cancer, underlying health conditions, past substance use, and family history, effectively combine all of these to paint a more complete picture of AI patient outcomes.”
Previously Focus wrote about the incredible function of telomeres. Now the researchers suggest that this will help monitor biological age and also warn about the development of cancer or inflammation.
Source: Focus
Ashley Fitzgerald is an accomplished journalist in the field of technology. She currently works as a writer at 24 news breaker. With a deep understanding of the latest technology developments, Ashley’s writing provides readers with insightful analysis and unique perspectives on the industry.